La recerca s'articula en dues línies amb els objectius que es detallen a continuació.

Percepció i Manipulació:
1. Enllaçar percepció i acció utilitzant mètodes geomètrics i estadístics per al modelatge de l'entorn i del propi robot, per a la planificació de tasques i moviments, i per a l'aprenentatge.
2. Aprofundir en l'aprenentatge per reforçament i en l'aprenentatge per demostració, en particular el "mestratge", com a base per a la interacció entre robots, humans i l'entorn.

Cinemàtica i Disseny de Robots:
3. Trobar mètodes generals i complets per a l'anàlisi i la planificació de moviments lliures de col·lisió de mecanismes.
4. Desenvolupar noves estructures mecàniques, preferentment robots paral·lels i robots basats en estructures "tensegrity".
5. Incrementar i millorar l'expertesa del grup en l'àrea del disseny mecànic

http://futur.upc.edu/ROBiri


La investigación se articula en dos líneas con los objectivos que se detallan a continuación.

Percepción y Manipulación:
1. Enlazar percepción y acción utilitzando métodos geométricos y estadísticos para el modelado del entorno y del propio robot, para la planificación de tareas y movimientos, y para el aprendizaje.
2. Profundizar en el aprendizaje por refuerzo y en el aprendizaje por demostración, en particular el entrenamiento, como base para la interacción entre robots, humanos y el entorno.

Cinemática y Diseño de Robots:
3. Encontrar métodos generales y completos para análisis y planificación de movimientos libres de colisión.
4. Desarrollar nuevas estructuras mecánicas, preferentmente robots paralelos y robots "tensegrity".
5. Incrementar y mejorar la competencia del grupo en el área del diseño mecánico.

http://futur.upc.edu/ROBiri


Research is organized in two lines with the following goals.

Perception and Manipulation:
1. Linking perception and action using geometric and statistic methods for modelling the environment and the robot, for task and motion planning, and for learning.
2. Deepening on reinforcement learning and in learning by demonstration, in particular "coaching", as a basis for the interaction of robots, humans and the environtment.

Kinematics and Robot Design:
3. Finding general and complete methods for the analysis of mechanisms and for planning collision-free motions.
4. Developing new mechanical structures, especially parallel robots and robots based on tensegrity structures.
5. Increasing and enhancing the expertise of the group in the area of mechanical design.

http://futur.upc.edu/ROBiri


Research is organized in two lines with the following goals.

Perception and Manipulation:
1. Linking perception and action using geometric and statistic methods for modelling the environment and the robot, for task and motion planning, and for learning.
2. Deepening on reinforcement learning and in learning by demonstration, in particular "coaching", as a basis for the interaction of robots, humans and the environtment.

Kinematics and Robot Design:
3. Finding general and complete methods for the analysis of mechanisms and for planning collision-free motions.
4. Developing new mechanical structures, especially parallel robots and robots based on tensegrity structures.
5. Increasing and enhancing the expertise of the group in the area of mechanical design.

http://futur.upc.edu/ROBiri

Envíos recientes

  • Depth-aware convolutional neural networks for accurate 3D pose estimation in RGB-D images 

    Porzi, Lorenzo; Peñate Sánchez, Adrián; Ricci, Elisa; Moreno-Noguer, Francesc (2017)
    Texto en actas de congreso
    Acceso abierto
    Most recent approaches to 3D pose estimation from RGB-D images address the problem in a two-stage pipeline. First, they learn a classifier –typically a random forest– to predict the position of each input pixel on the ...
  • 3D human pose estimation from a single image via distance matrix regression 

    Moreno-Noguer, Francesc (Institute of Electrical and Electronics Engineers (IEEE), 2017)
    Texto en actas de congreso
    Acceso abierto
    This paper addresses the problem of 3D human pose estimation from a single image. We follow a standard two-step pipeline by first detecting the 2D position of the N body joints, and then using these observations to infer ...
  • 3D CNNs on distance matrices for human action recognition 

    Hernández Ruiz, Alejandro José; Porzi, Lorenzo; Rota Bulò, Samuel; Moreno-Noguer, Francesc (2017)
    Texto en actas de congreso
    Acceso abierto
    In this paper we are interested in recognizing human actions from sequences of 3D skeleton data. For this purpose we combine a 3D Convolutional Neural Network with body representations based on Euclidean Distance Matrices ...
  • Multi-modal embedding for main product detection in fashion 

    Rubio Romano, Antonio; LongLong, Yu; Simo Serra, Edgar; Moreno-Noguer, Francesc (2017)
    Texto en actas de congreso
    Acceso abierto
    We present an approach to detect the main product in fashion images by exploiting the textual metadata associated with each image. Our approach is based on a Convolutional Neural Network and learns a joint embedding of ...
  • Low resolution lidar-based multi object tracking for driving applications 

    del Pino Bastida, Iván; Vaquero Gómez, Víctor; Massini, Beatrice; Solà Ortega, Joan; Moreno-Noguer, Francesc; Sanfeliu Cortés, Alberto; Andrade-Cetto, Juan (Springer, 2017)
    Texto en actas de congreso
    Acceso abierto
    Vehicle detection and tracking in real scenarios are key com- ponents to develop assisted and autonomous driving systems. Lidar sen- sors are specially suitable for this task, as they bring robustness to harsh weather ...
  • Relational reinforcement learning for planning with exogenous effects 

    Martinez Martinez, David; Alenyà Ribas, Guillem; Ribeiro, Tony; Inoue, Katsumi; Torras, Carme (2017)
    Artículo
    Acceso abierto
    Probabilistic planners have improved recently to the point that they can solve difficult tasks with complex and expressive models. In contrast, learners cannot tackle yet the expressive models that planners do, which forces ...
  • Relational reinforcement learning with guided demonstrations 

    Martínez Martínez, David; Alenyà Ribas, Guillem; Torras, Carme (2017)
    Artículo
    Acceso abierto
    Model-based reinforcement learning is a powerful paradigm for learning tasks in robotics. However, in-depth exploration is usually required and the actions have to be known in advance. Thus, we propose a novel algorithm ...
  • Visual grasp point localization, classification and state recognition in robotic manipulation of cloth: an overview 

    Jimenez Schlegl, Pablo (2017)
    Artículo
    Acceso abierto
    Cloth manipulation by robots is gaining popularity among researchers because of its relevance, mainly (but not only) in domestic and assistive robotics. The required science and technologies begin to be ripe for the ...
  • Random clustering ferns for multimodal object recognition 

    Villamizar Vergel, Michael Alejandro; Garrell Zulueta, Anais; Sanfeliu Cortés, Alberto; Moreno-Noguer, Francesc (2017-09-01)
    Artículo
    Acceso abierto
    We propose an efficient and robust method for the recognition of objects exhibiting multiple intra-class modes, where each one is associated with a particular object appearance. The proposed method, called random clustering ...
  • 3D human pose tracking priors using geodesic mixture models 

    Simo Serra, Edgar; Torras, Carme; Moreno-Noguer, Francesc (2017-04-01)
    Artículo
    Acceso abierto
    We present a novel approach for learning a finite mixture model on a Riemannian manifold in which Euclidean metrics are not applicable and one needs to resort to geodesic distances consistent with the manifold geometry. ...
  • ROS wrapper for real-time multi-person pose estimation with a single camera 

    Arduengo García, Miguel; Jorgensen, Steven Jens; Hambuchen, Kimberly; Sentis, Luis; Moreno-Noguer, Francesc; Alenyà Ribas, Guillem (2017)
    Report de recerca
    Acceso abierto
    For robots to be deployable in human occupied environments, the robots must have human-awareness and generate human-aware behaviors and policies. OpenPose is a library for real-time multi-person keypoint detection. We have ...
  • Dual REPS: a generalization of relative entropy policy search exploiting bad experiences 

    Colomé Figueras, Adrià; Torras, Carme (Institute of Electrical and Electronics Engineers (IEEE), 2017-08-01)
    Artículo
    Acceso abierto
    Policy search (PS) algorithms are widely used for their simplicity and effectiveness in finding solutions for robotic problems. However, most current PS algorithms derive policies by statistically fitting the data from the ...

Muestra más